MS Computer Science · AI Track · Binghamton University

Shreyas Khandale

ML Engineer·Quantum ML Researcher·RAG / LLM Systems

I design and ship machine-learning systems end to end — from Transformer surrogate models on quantum-network data to production RAG pipelines and IoT at the edge.

Shreyas Khandale, ML Engineer, in New York City
01 — About

Building production AI from edge to cloud

I'm a Master's student in Computer Science on the Artificial Intelligence and Machine Learning track at Binghamton University's Thomas J. Watson College. My work sits at the intersection of production ML engineering and applied research — shipping systems that hold up in the real world, then measuring them honestly.

Right now I'm integrating LLMs into a multi-tenant voice platform at Zoo Media and keeping a campus AI system running for ~24,000 students and staff. I recently completed research on Transformer-based surrogate models for quantum networks. Across all of it, I care about the same thing: real systems, real metrics, and being able to defend every number.

Earlier, I completed my BE in Computer Science & Engineering at Savitribai Phule Pune University - AISSMS College of Engineering, Pune, and published four papers across applied ML, NLP, and IoT.

Education
MS Computer Science (AI Track)Binghamton University · GPA 3.60 · Dec 2026
Now
AI Systems Integrator — Zoo Media+ Computing Services Admin · Binghamton ITS
Focus
ML Engineering · LLM/RAG · Quantum ML · IoT/Edge
Based in
Binghamton, NYOpen to relocate · US work authorized
02 — Experience

Where I work

AI Systems Integrator Intern
Feb 2026 — Present
Zoo Media Inc. · Remote
  • Architect a multi-tenant Voice AI Sales platform with an autonomous pipeline from CRM webhooks to AI-powered outbound calling — recognized as a 3-time "Outstanding Team Lead."
  • Restored a non-functional inherited codebase to a 90.9% test pass rate, debugging 79 runtime errors and 40 missing dependencies across ~45 files.
  • Lead 9 developers across a 6-workstream roadmap spanning AI/LLM, voice (ElevenLabs), telephony (RingCentral), and cloud.
Computing Services Admin
Jan 2025 — Present
Information Technology Services, Binghamton University
  • Administer a production AI conversational system serving ~24,000 students and staff, applying SRE practices and automated health checks.
  • Engineered a continuous NLP retraining and evaluation pipeline sustaining a ~90% ticket-resolution rate.
  • Maintain 24/7 availability via real-time PRTG monitoring, triaging and escalating incidents to Network Engineering.
Graduate Research Assistant
Jan 2025 — May 2026
Watson College, Binghamton University
  • Co-architected a Transformer encoder surrogate model for quantum networks — fusing channel embeddings with a multi-task head for joint channel classification and time regression.
  • Built a "digital cousin" simulation framework that replaces compute-heavy real-time digital twins with optimized statistical surrogates.
  • Engineered the data pipeline on EPB Quantum Network telemetry — America's first commercial quantum network — with N=200 sliding-window sequences and IQR normalization.
03 — Projects

Things I've built

A selection across production ML, GenAI, and embedded systems. Every metric below is measured, not estimated.

arXiv Paper Curator

150–400× latency cut

Production agentic RAG that ingests arXiv papers daily and answers grounded research questions. SHA-256 Redis caching over a hybrid BM25 + vector RRF pipeline; deployed to AWS EC2 at $0.

FastAPIOpenSearchRedisAirflowOllamaDocker

Cashflow Management

Forecasting + RAG

13-week cashflow forecasting with grounded natural-language Q&A and accounting-invariant enforcement — built as a production-style service, not a toy notebook.

XGBoostFastAPIPineconeGeminiMongoDB

Motion-Flow

In-browser ML

In-browser bidirectional sign-language translation across 40+ languages, 543 landmarks/frame at sub-second WebGPU latency. A re-implementation inspired by the open-source sign.mt project.

AngularTensorFlow.jsMediaPipeThree.js

Bayes Error Estimation

Research · ICLR 2023

Reproduces and extends Ishida et al. (ICLR 2023), stress-testing soft-label Bayes-error estimation under annotation bias and miscalibration, with temperature-scaling calibration on CNN variants.

PyTorchNumPySciPy

Advanced Wine Quality

Ensemble + SHAP

Stacked ensemble (XGBoost + LightGBM + CatBoost) with SHAP interpretability and a FastAPI deployment — modeling plus explainability and serving.

scikit-learnXGBoostSHAPFastAPI

IoT Network-Attached Storage

Published · IJRASET 2024

Sub-$100 private NAS on a Raspberry Pi 4 with cross-platform SMB/CIFS access. Benchmarked four storage tiers and diagnosed Gigabit Ethernet — not disk speed — as the true network bottleneck.

Raspberry PiLinuxOpenMediaVaultSMB/CIFS

Smart Bicycle Theft Prevention

IoT · LoRaWAN

NFC authentication plus LoRaWAN tracking with a lock-state escalation model and a Flask dashboard, validated end-to-end over The Things Network.

Heltec LoRa 32nRF52840LoRaWANFlask

CallQA

Voice-AI QA

Automated voice-agent testing harness — 10 patient personas, Groq Whisper transcription, heuristic transcript analysis, and structured bug reports replacing manual call testing.

PythonTwilioGroq Whisper
04 — Stack

What I work with

Languages

PythonSQLC++TypeScriptCJavaBash

ML & Deep Learning

PyTorchscikit-learnXGBoostLightGBMCatBoostSHAPTransformersCNNsLSTMs

GenAI & LLMs

RAGLangGraphLangChainPrompt EngineeringHybrid Search (RRF)Vector EmbeddingsLangfuseOllama

Data & Backend

PandasNumPyFastAPIPostgreSQLOpenSearchRedisMongoDBAirflow

Cloud & Tooling

AWS (EC2/EBS)DockerGitGitHub ActionsLinux

Certifications

NVIDIA CUDA C/C++Google Advanced Data AnalyticsIBM Python for Data ScienceIBM Quantum InformationAdvanced Algorithms (BU)
05 — Research

Publications

Four peer-reviewed papers in IJRASET across applied ML, NLP, and IoT systems.

01

IoT-Based Network Attached Storage

IJRASET Vol.12, Nov 2024 · 10.22214/ijraset.2024.65616
02

Predicting Credit Card Defaults with Machine Learning

IJRASET Vol.11, Oct 2023 · 10.22214/ijraset.2023.55934
03

Stock Market Analysis Using Heuristic Approach

IJRASET Vol.11, Oct 2023 · 10.22214/ijraset.2023.55932
04

Amazon Fine Food Review Analysis

IJRASET Vol.11, Oct 2023 · 10.22214/ijraset.2023.55930
06 — Contact

Let's talk

I'm looking for ML / AI Engineer roles. If you're hiring or just want to compare notes on RAG systems or quantum ML, reach out.